{"total":20,"rows":[{"id":"2302.10805","title":"Repeated Bilateral Trade Against a Smoothed Adversary","created":"2023-02-21","cited_by_count":15,"area":null},{"id":"2103.00360","title":"Exploration and Incentives in Reinforcement Learning","created":"2021-02-28","cited_by_count":11,"area":null},{"id":"2109.11679","title":"Safe Policy Learning through Extrapolation: Application to Pre-trial Risk Assessment","created":"2021-09-22","cited_by_count":10,"area":null},{"id":"2110.12175","title":"Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits","created":"2021-10-23","cited_by_count":10,"area":null},{"id":"2306.06250","title":"Strategic Apple Tasting","created":"2023-06-09","cited_by_count":10,"area":null},{"id":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","cited_by_count":7,"area":null},{"id":"2302.07425","title":"Bandit Social Learning: Exploration under Myopic Behavior","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2211.15381","title":"Incentive-Aware Recommender Systems in Two-Sided Markets","created":"2022-11-23","cited_by_count":5,"area":null},{"id":"2402.10289","title":"Thompson Sampling in Partially Observable Contextual Bandits","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2109.14412","title":"Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification","created":"2021-09-29","cited_by_count":3,"area":null},{"id":"2202.00867","title":"Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2501.00891","title":"Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2402.13338","title":"Incentivized Exploration via Filtered Posterior Sampling","created":"2024-02-20","cited_by_count":2,"area":null},{"id":"2503.04010","title":"Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2410.17086","title":"Exploration and Persuasion","created":"2024-10-22","cited_by_count":1,"area":null},{"id":"2510.26000","title":"Infrequent Exploration in Linear Bandits","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2602.20465","title":"Prior-Agnostic Incentive-Compatible Exploration","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2605.09119","title":"Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2609.28718","title":"Exact Bayes Regret and Asymptotic Optimality in High-Dimensional Gaussian Bandits","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.30321","title":"Adaptive Random Matrices in Gaussian Bandits: Spectral Universality and Selection-Induced Outliers","created":"2026-09-23","cited_by_count":0,"area":null}],"next_cursor":null}